European Pro League Series 8 Closed Qualifier · BO3
result vs predictionseries probability
50%50%
probability at match start · final 2:1
The prediction was locked in using data as of the match start: map winrates, form and head-to-head were computed only from games before it began. This is how the model's honest accuracy is verified.
Map veto prediction
For each map — both teams' winrate over 3 months. The model guesses who bans it and who keeps it: teams remove maps where they are weaker and pull toward their strong ones.
Dust2ex-MANA pick
60%33%
ex-MANA · 1 mapedge ex-MANA +27%Subtop De France · 2 maps
Infernoex-MANA ban
50%33%
ex-MANA · 0 mapsedge ex-MANA +17%Subtop De France · 2 maps
AncientSubtop De France ban
50%40%
ex-MANA · 0 mapsedge ex-MANA +10%Subtop De France · 1 map
CacheSubtop De France pick
50%60%
ex-MANA · 0 mapsedge Subtop De France +10%Subtop De France · 1 map
MirageSubtop De France ban
60%50%
ex-MANA · 1 mapedge ex-MANA +10%Subtop De France · 0 maps
Nukeex-MANA ban
50%60%
ex-MANA · 0 mapsedge Subtop De France +10%Subtop De France · 1 map
Most likely veto scenario
1. Banex-MANA remove Nuke
2. BanSubtop De France remove Mirage
3. Pickex-MANA take Dust2
4. PickSubtop De France take Cache
5. BanSubtop De France remove Ancient
6. Banex-MANA remove Inferno
Prediction by map vs result
Probabilities were locked in using statistics as of the match start (map winrate over the 3 months before it). We compare against the actual result of each map.
Dust2prediction correct13:6
ex-MANA 77%Subtop De France 23%
The model gave 77% on ex-MANA — the map was taken by ex-MANA.
Defaultprediction missed0:1
ex-MANA 50%Subtop De France 50%
The model gave 50% on ex-MANA — the map was taken by Subtop De France.
Nukeprediction missed13:4
ex-MANA 40%Subtop De France 60%
The model gave 60% on Subtop De France — the map was taken by ex-MANA.
Model check result
Model favoriteex-MANA · 50%
Series resultex-MANA 2:1
Series predictioncorrect
Accuracy by map1 of 3